In [1]:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline
from sklearn.datasets import load_breast_cancer
import seaborn as sns
In [2]:
cancer= load_breast_cancer()
cancer.keys()
Out[2]:
dict_keys(['data', 'target', 'frame', 'target_names', 'DESCR', 'feature_names', 'filename', 'data_module'])
In [3]:
cancer.data
Out[3]:
array([[1.799e+01, 1.038e+01, 1.228e+02, ..., 2.654e-01, 4.601e-01,
        1.189e-01],
       [2.057e+01, 1.777e+01, 1.329e+02, ..., 1.860e-01, 2.750e-01,
        8.902e-02],
       [1.969e+01, 2.125e+01, 1.300e+02, ..., 2.430e-01, 3.613e-01,
        8.758e-02],
       ...,
       [1.660e+01, 2.808e+01, 1.083e+02, ..., 1.418e-01, 2.218e-01,
        7.820e-02],
       [2.060e+01, 2.933e+01, 1.401e+02, ..., 2.650e-01, 4.087e-01,
        1.240e-01],
       [7.760e+00, 2.454e+01, 4.792e+01, ..., 0.000e+00, 2.871e-01,
        7.039e-02]])
In [4]:
cancer.target
Out[4]:
array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0,
       0, 0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 0, 0, 1, 1, 1, 1, 0, 1, 0, 0,
       1, 1, 1, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0, 1, 1, 1, 0, 0, 1, 0, 0, 0,
       1, 1, 1, 0, 1, 1, 0, 0, 1, 1, 1, 0, 0, 1, 1, 1, 1, 0, 1, 1, 0, 1,
       1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 1, 1, 1, 0, 0, 1, 0, 1, 0,
       0, 1, 0, 0, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 0, 1, 1, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 0, 1, 1, 1,
       1, 0, 1, 1, 0, 0, 0, 1, 0, 1, 0, 1, 1, 1, 0, 1, 1, 0, 0, 1, 0, 0,
       0, 0, 1, 0, 0, 0, 1, 0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0,
       1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 0, 1, 1, 0, 0, 1, 0, 1, 1,
       1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 0, 1, 0, 0, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0,
       0, 1, 1, 1, 1, 0, 1, 0, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0,
       0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 0, 0, 0, 1, 0, 0,
       1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 0, 0, 1, 1,
       1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 0,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 0, 1, 0, 1, 1, 1, 1,
       1, 0, 1, 1, 0, 1, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0,
       1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1,
       1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 0, 1, 0, 1, 1,
       1, 1, 1, 0, 1, 1, 0, 1, 0, 1, 0, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1])
In [5]:
cancer.target_names
Out[5]:
array(['malignant', 'benign'], dtype='<U9')
In [6]:
cancer.DESCR
Out[6]:
'.. _breast_cancer_dataset:\n\nBreast cancer wisconsin (diagnostic) dataset\n--------------------------------------------\n\n**Data Set Characteristics:**\n\n    :Number of Instances: 569\n\n    :Number of Attributes: 30 numeric, predictive attributes and the class\n\n    :Attribute Information:\n        - radius (mean of distances from center to points on the perimeter)\n        - texture (standard deviation of gray-scale values)\n        - perimeter\n        - area\n        - smoothness (local variation in radius lengths)\n        - compactness (perimeter^2 / area - 1.0)\n        - concavity (severity of concave portions of the contour)\n        - concave points (number of concave portions of the contour)\n        - symmetry\n        - fractal dimension ("coastline approximation" - 1)\n\n        The mean, standard error, and "worst" or largest (mean of the three\n        worst/largest values) of these features were computed for each image,\n        resulting in 30 features.  For instance, field 0 is Mean Radius, field\n        10 is Radius SE, field 20 is Worst Radius.\n\n        - class:\n                - WDBC-Malignant\n                - WDBC-Benign\n\n    :Summary Statistics:\n\n    ===================================== ====== ======\n                                           Min    Max\n    ===================================== ====== ======\n    radius (mean):                        6.981  28.11\n    texture (mean):                       9.71   39.28\n    perimeter (mean):                     43.79  188.5\n    area (mean):                          143.5  2501.0\n    smoothness (mean):                    0.053  0.163\n    compactness (mean):                   0.019  0.345\n    concavity (mean):                     0.0    0.427\n    concave points (mean):                0.0    0.201\n    symmetry (mean):                      0.106  0.304\n    fractal dimension (mean):             0.05   0.097\n    radius (standard error):              0.112  2.873\n    texture (standard error):             0.36   4.885\n    perimeter (standard error):           0.757  21.98\n    area (standard error):                6.802  542.2\n    smoothness (standard error):          0.002  0.031\n    compactness (standard error):         0.002  0.135\n    concavity (standard error):           0.0    0.396\n    concave points (standard error):      0.0    0.053\n    symmetry (standard error):            0.008  0.079\n    fractal dimension (standard error):   0.001  0.03\n    radius (worst):                       7.93   36.04\n    texture (worst):                      12.02  49.54\n    perimeter (worst):                    50.41  251.2\n    area (worst):                         185.2  4254.0\n    smoothness (worst):                   0.071  0.223\n    compactness (worst):                  0.027  1.058\n    concavity (worst):                    0.0    1.252\n    concave points (worst):               0.0    0.291\n    symmetry (worst):                     0.156  0.664\n    fractal dimension (worst):            0.055  0.208\n    ===================================== ====== ======\n\n    :Missing Attribute Values: None\n\n    :Class Distribution: 212 - Malignant, 357 - Benign\n\n    :Creator:  Dr. William H. Wolberg, W. Nick Street, Olvi L. Mangasarian\n\n    :Donor: Nick Street\n\n    :Date: November, 1995\n\nThis is a copy of UCI ML Breast Cancer Wisconsin (Diagnostic) datasets.\nhttps://goo.gl/U2Uwz2\n\nFeatures are computed from a digitized image of a fine needle\naspirate (FNA) of a breast mass.  They describe\ncharacteristics of the cell nuclei present in the image.\n\nSeparating plane described above was obtained using\nMultisurface Method-Tree (MSM-T) [K. P. Bennett, "Decision Tree\nConstruction Via Linear Programming." Proceedings of the 4th\nMidwest Artificial Intelligence and Cognitive Science Society,\npp. 97-101, 1992], a classification method which uses linear\nprogramming to construct a decision tree.  Relevant features\nwere selected using an exhaustive search in the space of 1-4\nfeatures and 1-3 separating planes.\n\nThe actual linear program used to obtain the separating plane\nin the 3-dimensional space is that described in:\n[K. P. Bennett and O. L. Mangasarian: "Robust Linear\nProgramming Discrimination of Two Linearly Inseparable Sets",\nOptimization Methods and Software 1, 1992, 23-34].\n\nThis database is also available through the UW CS ftp server:\n\nftp ftp.cs.wisc.edu\ncd math-prog/cpo-dataset/machine-learn/WDBC/\n\n.. topic:: References\n\n   - W.N. Street, W.H. Wolberg and O.L. Mangasarian. Nuclear feature extraction \n     for breast tumor diagnosis. IS&T/SPIE 1993 International Symposium on \n     Electronic Imaging: Science and Technology, volume 1905, pages 861-870,\n     San Jose, CA, 1993.\n   - O.L. Mangasarian, W.N. Street and W.H. Wolberg. Breast cancer diagnosis and \n     prognosis via linear programming. Operations Research, 43(4), pages 570-577, \n     July-August 1995.\n   - W.H. Wolberg, W.N. Street, and O.L. Mangasarian. Machine learning techniques\n     to diagnose breast cancer from fine-needle aspirates. Cancer Letters 77 (1994) \n     163-171.'
In [7]:
cancer.feature_names
Out[7]:
array(['mean radius', 'mean texture', 'mean perimeter', 'mean area',
       'mean smoothness', 'mean compactness', 'mean concavity',
       'mean concave points', 'mean symmetry', 'mean fractal dimension',
       'radius error', 'texture error', 'perimeter error', 'area error',
       'smoothness error', 'compactness error', 'concavity error',
       'concave points error', 'symmetry error',
       'fractal dimension error', 'worst radius', 'worst texture',
       'worst perimeter', 'worst area', 'worst smoothness',
       'worst compactness', 'worst concavity', 'worst concave points',
       'worst symmetry', 'worst fractal dimension'], dtype='<U23')
In [8]:
df= pd.DataFrame(np.c_[cancer['data'], cancer['target']], columns=np.append(cancer['feature_names'],['target']))
df
Out[8]:
mean radius mean texture mean perimeter mean area mean smoothness mean compactness mean concavity mean concave points mean symmetry mean fractal dimension ... worst texture worst perimeter worst area worst smoothness worst compactness worst concavity worst concave points worst symmetry worst fractal dimension target
0 17.99 10.38 122.80 1001.0 0.11840 0.27760 0.30010 0.14710 0.2419 0.07871 ... 17.33 184.60 2019.0 0.16220 0.66560 0.7119 0.2654 0.4601 0.11890 0.0
1 20.57 17.77 132.90 1326.0 0.08474 0.07864 0.08690 0.07017 0.1812 0.05667 ... 23.41 158.80 1956.0 0.12380 0.18660 0.2416 0.1860 0.2750 0.08902 0.0
2 19.69 21.25 130.00 1203.0 0.10960 0.15990 0.19740 0.12790 0.2069 0.05999 ... 25.53 152.50 1709.0 0.14440 0.42450 0.4504 0.2430 0.3613 0.08758 0.0
3 11.42 20.38 77.58 386.1 0.14250 0.28390 0.24140 0.10520 0.2597 0.09744 ... 26.50 98.87 567.7 0.20980 0.86630 0.6869 0.2575 0.6638 0.17300 0.0
4 20.29 14.34 135.10 1297.0 0.10030 0.13280 0.19800 0.10430 0.1809 0.05883 ... 16.67 152.20 1575.0 0.13740 0.20500 0.4000 0.1625 0.2364 0.07678 0.0
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...
564 21.56 22.39 142.00 1479.0 0.11100 0.11590 0.24390 0.13890 0.1726 0.05623 ... 26.40 166.10 2027.0 0.14100 0.21130 0.4107 0.2216 0.2060 0.07115 0.0
565 20.13 28.25 131.20 1261.0 0.09780 0.10340 0.14400 0.09791 0.1752 0.05533 ... 38.25 155.00 1731.0 0.11660 0.19220 0.3215 0.1628 0.2572 0.06637 0.0
566 16.60 28.08 108.30 858.1 0.08455 0.10230 0.09251 0.05302 0.1590 0.05648 ... 34.12 126.70 1124.0 0.11390 0.30940 0.3403 0.1418 0.2218 0.07820 0.0
567 20.60 29.33 140.10 1265.0 0.11780 0.27700 0.35140 0.15200 0.2397 0.07016 ... 39.42 184.60 1821.0 0.16500 0.86810 0.9387 0.2650 0.4087 0.12400 0.0
568 7.76 24.54 47.92 181.0 0.05263 0.04362 0.00000 0.00000 0.1587 0.05884 ... 30.37 59.16 268.6 0.08996 0.06444 0.0000 0.0000 0.2871 0.07039 1.0

569 rows × 31 columns

In [9]:
df.shape
Out[9]:
(569, 31)
In [10]:
df.isnull().sum()
Out[10]:
mean radius                0
mean texture               0
mean perimeter             0
mean area                  0
mean smoothness            0
mean compactness           0
mean concavity             0
mean concave points        0
mean symmetry              0
mean fractal dimension     0
radius error               0
texture error              0
perimeter error            0
area error                 0
smoothness error           0
compactness error          0
concavity error            0
concave points error       0
symmetry error             0
fractal dimension error    0
worst radius               0
worst texture              0
worst perimeter            0
worst area                 0
worst smoothness           0
worst compactness          0
worst concavity            0
worst concave points       0
worst symmetry             0
worst fractal dimension    0
target                     0
dtype: int64
In [11]:
df.describe()
Out[11]:
mean radius mean texture mean perimeter mean area mean smoothness mean compactness mean concavity mean concave points mean symmetry mean fractal dimension ... worst texture worst perimeter worst area worst smoothness worst compactness worst concavity worst concave points worst symmetry worst fractal dimension target
count 569.000000 569.000000 569.000000 569.000000 569.000000 569.000000 569.000000 569.000000 569.000000 569.000000 ... 569.000000 569.000000 569.000000 569.000000 569.000000 569.000000 569.000000 569.000000 569.000000 569.000000
mean 14.127292 19.289649 91.969033 654.889104 0.096360 0.104341 0.088799 0.048919 0.181162 0.062798 ... 25.677223 107.261213 880.583128 0.132369 0.254265 0.272188 0.114606 0.290076 0.083946 0.627417
std 3.524049 4.301036 24.298981 351.914129 0.014064 0.052813 0.079720 0.038803 0.027414 0.007060 ... 6.146258 33.602542 569.356993 0.022832 0.157336 0.208624 0.065732 0.061867 0.018061 0.483918
min 6.981000 9.710000 43.790000 143.500000 0.052630 0.019380 0.000000 0.000000 0.106000 0.049960 ... 12.020000 50.410000 185.200000 0.071170 0.027290 0.000000 0.000000 0.156500 0.055040 0.000000
25% 11.700000 16.170000 75.170000 420.300000 0.086370 0.064920 0.029560 0.020310 0.161900 0.057700 ... 21.080000 84.110000 515.300000 0.116600 0.147200 0.114500 0.064930 0.250400 0.071460 0.000000
50% 13.370000 18.840000 86.240000 551.100000 0.095870 0.092630 0.061540 0.033500 0.179200 0.061540 ... 25.410000 97.660000 686.500000 0.131300 0.211900 0.226700 0.099930 0.282200 0.080040 1.000000
75% 15.780000 21.800000 104.100000 782.700000 0.105300 0.130400 0.130700 0.074000 0.195700 0.066120 ... 29.720000 125.400000 1084.000000 0.146000 0.339100 0.382900 0.161400 0.317900 0.092080 1.000000
max 28.110000 39.280000 188.500000 2501.000000 0.163400 0.345400 0.426800 0.201200 0.304000 0.097440 ... 49.540000 251.200000 4254.000000 0.222600 1.058000 1.252000 0.291000 0.663800 0.207500 1.000000

8 rows × 31 columns

In [12]:
df.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 569 entries, 0 to 568
Data columns (total 31 columns):
 #   Column                   Non-Null Count  Dtype  
---  ------                   --------------  -----  
 0   mean radius              569 non-null    float64
 1   mean texture             569 non-null    float64
 2   mean perimeter           569 non-null    float64
 3   mean area                569 non-null    float64
 4   mean smoothness          569 non-null    float64
 5   mean compactness         569 non-null    float64
 6   mean concavity           569 non-null    float64
 7   mean concave points      569 non-null    float64
 8   mean symmetry            569 non-null    float64
 9   mean fractal dimension   569 non-null    float64
 10  radius error             569 non-null    float64
 11  texture error            569 non-null    float64
 12  perimeter error          569 non-null    float64
 13  area error               569 non-null    float64
 14  smoothness error         569 non-null    float64
 15  compactness error        569 non-null    float64
 16  concavity error          569 non-null    float64
 17  concave points error     569 non-null    float64
 18  symmetry error           569 non-null    float64
 19  fractal dimension error  569 non-null    float64
 20  worst radius             569 non-null    float64
 21  worst texture            569 non-null    float64
 22  worst perimeter          569 non-null    float64
 23  worst area               569 non-null    float64
 24  worst smoothness         569 non-null    float64
 25  worst compactness        569 non-null    float64
 26  worst concavity          569 non-null    float64
 27  worst concave points     569 non-null    float64
 28  worst symmetry           569 non-null    float64
 29  worst fractal dimension  569 non-null    float64
 30  target                   569 non-null    float64
dtypes: float64(31)
memory usage: 137.9 KB

Data Visualization¶

In [13]:
sns.pairplot(df, hue='target')
plt.show()
In [14]:
sns.pairplot(df ,hue ='target', vars =['mean radius','mean texture', 'mean perimeter', 'mean area',
 'mean smoothness', 'mean compactness' ,'mean concavity']) 
Out[14]:
<seaborn.axisgrid.PairGrid at 0x24bbbbef730>
In [15]:
sns.scatterplot(x='mean area', y='mean smoothness', hue='target', data=df)
Out[15]:
<AxesSubplot:xlabel='mean area', ylabel='mean smoothness'>
In [16]:
target_count=df.target.value_counts()
target_count
Out[16]:
1.0    357
0.0    212
Name: target, dtype: int64
In [17]:
target_count[0]=df[df['target']==0]
target_count[1]=df[df['target']==1]
In [18]:
plt.figure(figsize=(8,6))
plt.title('Target Distribution')
sns.countplot(x=df['target'])
plt.show()
In [19]:
plt.figure(figsize=(20,12))
sns.heatmap(df.corr(), annot=True)
Out[19]:
<AxesSubplot:>

Data Splitting¶

In [20]:
X= df.drop(['target'], axis='columns')
y= df.target

Normalization/Scaling¶

In [23]:
from sklearn.preprocessing import StandardScaler
scaler= StandardScaler()
scaler.fit(X)
X_scaled= scaler.fit_transform(X)
In [24]:
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test= train_test_split(X_scaled, y, test_size=0.2, random_state=20)
In [26]:
X_train
Out[26]:
array([[-1.34347001,  0.55625084, -1.32710844, ..., -1.35465286,
        -0.84893962,  0.44965407],
       [ 3.77531785,  1.62437465,  3.91022552, ...,  2.251919  ,
        -0.42022775, -0.53619332],
       [-0.1270372 , -0.68873007, -0.17337093, ..., -0.41973978,
        -0.15329395, -0.33946717],
       ...,
       [-0.80583113, -1.45433516, -0.81305474, ..., -0.41273555,
        -0.27139194, -0.20646921],
       [-0.92227695, -0.85395184, -0.8880209 , ..., -0.53211207,
        -0.51729459,  1.3329822 ],
       [-0.4451331 , -0.05111368, -0.4139217 , ..., -0.33431857,
        -1.26147367, -0.66863712]])
In [36]:
y_train
Out[36]:
412    1.0
461    0.0
532    1.0
495    1.0
13     0.0
      ... 
218    0.0
223    0.0
271    1.0
474    1.0
355    1.0
Name: target, Length: 455, dtype: float64

dimentionality reduction¶

In [37]:
from sklearn.decomposition import PCA
pca= PCA(0.95)
X_pca=pca.fit_transform(X_scaled)
X_pca.shape
Out[37]:
(569, 10)
In [38]:
#Compare data before and after pca
print(X.shape)
print(X_pca.shape)
(569, 30)
(569, 10)
In [40]:
plt.figure(figsize=(8,6))
plt.scatter(X_pca[:,0],X_pca[:,1], c=y, cmap='plasma')
plt.xlabel("First Principle Component")
plt.ylabel("Second Principle Component")
Out[40]:
Text(0, 0.5, 'Second Principle Component')
In [41]:
pca.explained_variance_ratio_
Out[41]:
array([0.44272026, 0.18971182, 0.09393163, 0.06602135, 0.05495768,
       0.04024522, 0.02250734, 0.01588724, 0.01389649, 0.01168978])
In [42]:
pca.n_components_
Out[42]:
10
In [45]:
X_train_pca, X_test_pca, y_train, y_test= train_test_split(X_pca,y, test_size=0.2, random_state=20)
print(X_train_pca.shape)
print(X_test_pca.shape)
(455, 10)
(114, 10)

Model Training¶

In [52]:
def get_score(model, X_train, X_test, y_train, y_test):
    model.fit(X_train, y_train)
    return model.score(X_test, y_test)
In [53]:
from sklearn.svm import SVC
from sklearn.naive_bayes import GaussianNB
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import StratifiedKFold
from sklearn.model_selection import KFold
In [54]:
folds= StratifiedKFold(n_splits=3)

scores_svm= []
scores_naive= []
scores_randomforest= []

for train_index, test_index in folds.split(X_pca, y):
    X_train, X_test= X_pca[train_index], X_pca[test_index]
    y_train, y_test= y[train_index], y[test_index]
    scores_svm.append(get_score(SVC(), X_train, X_test, y_train, y_test))
    scores_naive.append(get_score(GaussianNB(), X_train, X_test, y_train, y_test))
    scores_randomforest.append(get_score(RandomForestClassifier(), X_train, X_test, y_train, y_test))
In [56]:
print(scores_svm)
print(scores_naive)
print(scores_randomforest)
[0.968421052631579, 0.9789473684210527, 0.9735449735449735]
[0.9052631578947369, 0.9263157894736842, 0.9259259259259259]
[0.9263157894736842, 0.968421052631579, 0.9365079365079365]
In [60]:
from sklearn.svm import SVC
model= SVC()
model.fit(X_train, y_train)
model.score(X_test, y_test)
Out[60]:
0.9735449735449735
In [63]:
y_pred=model.predict(X_test)
y_pred
Out[63]:
array([0., 0., 0., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
       0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
       0., 1., 1., 0., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 0.,
       1., 0., 0., 1., 0., 1., 1., 1., 1., 1., 0., 1., 1., 0., 1., 0., 1.,
       1., 0., 1., 0., 1., 1., 1., 1., 1., 1., 1., 1., 0., 0., 1., 1., 1.,
       1., 1., 1., 0., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 0., 1., 1.,
       1., 1., 1., 1., 1., 0., 1., 0., 1., 1., 0., 1., 1., 1., 1., 1., 0.,
       0., 1., 0., 1., 0., 0., 1., 1., 1., 1., 0., 1., 1., 0., 1., 0., 1.,
       0., 0., 1., 1., 1., 0., 1., 1., 1., 1., 0., 1., 1., 1., 1., 1., 1.,
       0., 1., 0., 0., 1., 1., 1., 1., 0., 1., 1., 1., 1., 1., 1., 1., 1.,
       1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 1., 0., 0., 0., 0., 0.,
       0., 1.])

Model Evaluation¶

In [64]:
from sklearn.metrics import confusion_matrix, classification_report
cm= confusion_matrix(y_test, y_pred)
sns.heatmap(cm, annot=True, fmt='d')
Out[64]:
<AxesSubplot:>
In [65]:
print(classification_report(y_test, y_pred))
              precision    recall  f1-score   support

         0.0       0.95      0.99      0.97        70
         1.0       0.99      0.97      0.98       119

    accuracy                           0.97       189
   macro avg       0.97      0.98      0.97       189
weighted avg       0.97      0.97      0.97       189

In [ ]: